activity
20162026
most citedWhetstone: A Method for Training Deep Artificial Neural Networks for Binary Communication

96 citations · 260 across the 26 of their papers we have counts for

collaborators
Showing 2017Show all

6 papers · 1 filter

cs.CR2017

Tracking Cyber Adversaries with Adaptive Indicators of Compromise

Justin E. Doak, Joe B. Ingram, Sam A. Mulder +6

A forensics investigation after a breach often uncovers network and host indicators of compromise (IOCs) that can be deployed to sensors to allow early detection of the adversary i…

stat.ML2017★ 1 cited

Context-modulation of hippocampal dynamics and deep convolutional networks

James B. Aimone, William M. Severa

Complex architectures of biological neural circuits, such as parallel processing pathways, has been behaviorally implicated in many cognitive studies. However, the theoretical cons…

cs.CR2017

Dynamic Analysis of Executables to Detect and Characterize Malware

Michael R. Smith, Joe B. Ingram, Christopher C. Lamb +4

It is needed to ensure the integrity of systems that process sensitive information and control many aspects of everyday life. We examine the use of machine learning algorithms to d…

cs.NE2017

Data-driven Feature Sampling for Deep Hyperspectral Classification and Segmentation

William M. Severa, Jerilyn A. Timlin, Suraj Kholwadwala +2

The high dimensionality of hyperspectral imaging forces unique challenges in scope, size and processing requirements. Motivated by the potential for an in-the-field cell sorting de…

cs.NE2017

Exponential scaling of neural algorithms - a future beyond Moore's Law?

James B. Aimone

Although the brain has long been considered a potential inspiration for future computing, Moore's Law - the scaling property that has seen revolutions in technologies ranging from…

q-bio.NC2017

A Digital Neuromorphic Architecture Efficiently Facilitating Complex Synaptic Response Functions Applied to Liquid State Machines

Michael R. Smith, Aaron J. Hill, Kristofor D. Carlson +7

Information in neural networks is represented as weighted connections, or synapses, between neurons. This poses a problem as the primary computational bottleneck for neural network…